upgini 1.2.71a3832.dev13__py3-none-any.whl → 1.2.72__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.71a3832.dev13"
+__version__ = "1.2.72"

upgini/features_enricher.py

@@ -3250,8 +3250,7 @@ if response.status_code == 200:
     def _validate_eval_set_pair(self, X: pd.DataFrame, eval_pair: Tuple) -> Tuple[pd.DataFrame, pd.Series]:
         if len(eval_pair) != 2:
             raise ValidationError(self.bundle.get("eval_set_invalid_tuple_size").format(len(eval_pair)))
-        eval_X = eval_pair[0]
-        eval_y = eval_pair[1]
+        eval_X, eval_y = eval_pair
 
         if _num_samples(eval_X) == 0:
             raise ValidationError(self.bundle.get("eval_x_is_empty"))

upgini/metrics.py

@@ -8,18 +8,18 @@ from copy import deepcopy
 from dataclasses import dataclass
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
+import lightgbm as lgb
 import numpy as np
 import pandas as pd
 from lightgbm import LGBMClassifier, LGBMRegressor
-import lightgbm as lgb
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
-# from sklearn.calibration import LabelEncoder
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
 from sklearn.preprocessing import OrdinalEncoder
 
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
+from upgini.utils.blocked_time_series import BlockedTimeSeriesSplit
 
 try:
     from sklearn.metrics import get_scorer_names
@@ -31,7 +31,7 @@ except ImportError:
     available_scorers = SCORERS
 from sklearn.metrics import mean_squared_error
 from sklearn.metrics._regression import _check_reg_targets, check_consistent_length
-from sklearn.model_selection import BaseCrossValidator
+from sklearn.model_selection import BaseCrossValidator, TimeSeriesSplit
 
 from upgini.errors import ValidationError
 from upgini.metadata import ModelTaskType
@@ -85,22 +85,6 @@ CATBOOST_MULTICLASS_PARAMS = {
     "auto_class_weights": "Balanced",
 }
 
-LIGHTGBM_PARAMS = {
-    "random_state": DEFAULT_RANDOM_STATE,
-    # "num_leaves": 16,
-    # "n_estimators": 150,
-    # "min_child_weight": 1,
-    "max_depth": 4,
-    "max_cat_threshold": 80,
-    "min_data_per_group": 25,
-    "num_boost_round": 150,
-    "cat_l2": 10,
-    "cat_smooth": 12,
-    "learning_rate": 0.05,
-    "feature_fraction": 1.0,
-    "min_sum_hessian_in_leaf": 0.01,
-}
-
 LIGHTGBM_REGRESSION_PARAMS = {
     "random_state": DEFAULT_RANDOM_STATE,
     "deterministic": True,
@@ -127,9 +111,9 @@ LIGHTGBM_MULTICLASS_PARAMS = {
     "max_cat_threshold": 80,
     "min_data_per_group": 20,
     "cat_smooth": 18,
-    "cat_l2" : 8,
+    "cat_l2": 8,
     "objective": "multiclass",
-    "class_weight": "balanced",
+    # "class_weight": "balanced",
     "use_quantized_grad": "true",
     "num_grad_quant_bins": "8",
     "stochastic_rounding": "true",
@@ -143,12 +127,12 @@ LIGHTGBM_BINARY_PARAMS = {
     "max_depth": 5,
     "learning_rate": 0.05,
     "objective": "binary",
-    "class_weight": "balanced",
+    # "class_weight": "balanced",
     "deterministic": True,
     "max_cat_threshold": 80,
     "min_data_per_group": 20,
     "cat_smooth": 18,
-    "cat_l2" : 8,
+    "cat_l2": 8,
     "verbosity": -1,
 }
 
@@ -507,7 +491,8 @@ class EstimatorWrapper:
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.REGRESSION:
-                params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
+                if not isinstance(cv, TimeSeriesSplit) and not isinstance(cv, BlockedTimeSeriesSplit):
+                    params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
             else:
@@ -756,7 +741,6 @@ class LightGBMWrapper(EstimatorWrapper):
             logger=logger,
         )
         self.cat_features = None
-        # self.cat_features_encoders = dict()
         self.cat_encoder = None
         self.n_classes = None
 
@@ -768,23 +752,13 @@ class LightGBMWrapper(EstimatorWrapper):
             params["callbacks"] = [lgb.early_stopping(stopping_rounds=LIGHTGBM_EARLY_STOPPING_ROUNDS, verbose=False)]
         self.cat_features = _get_cat_features(x)
         if self.cat_features:
-            params["categorical_feature"] = self.cat_features
-            # params["categorical_feature"] = [x.columns.get_loc(c) for c in self.cat_features] Works
-            # params["categorical_feature"] = "notauto"
-            # params["categorical_feature"] = "name:" + ",".join(self.cat_features)  # Doesn't work
-            # cat_indices = [str(x.columns.get_loc(c)) for c in self.cat_features] Doesn't work
-            # params["categorical_feature"] = ",".join(cat_indices)
-            pass
             x = fill_na_cat_features(x, self.cat_features)
             encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
-            encoded = encoder.fit_transform(x[self.cat_features], y_numpy)
+            encoded = pd.DataFrame(
+                encoder.fit_transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
+            )
             x[self.cat_features] = encoded
             self.cat_encoder = encoder
-        # for feature in self.cat_features:
-        #     encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
-        #     x[feature] = encoder.fit_transform(x[feature])
-        #     self.cat_features_encoders[feature] = encoder
-            # x[feature] = x[feature].astype("category").cat.codes
         if not is_numeric_dtype(y_numpy):
             y_numpy = correct_string_target(y_numpy)
 
@@ -793,19 +767,11 @@ class LightGBMWrapper(EstimatorWrapper):
     def _prepare_to_calculate(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
         x, y_numpy, params = super()._prepare_to_calculate(x, y)
         if self.cat_features is not None:
-            params["categorical_feature"] = self.cat_features
-            # params["categorical_feature"] = [x.columns.get_loc(c) for c in self.cat_features]
-            # params["categorical_feature"] = "notauto"
-            # params["categorical_feature"] = "name:" + ",".join(self.cat_features)  # Doesn't work
-            # cat_indices = [str(x.columns.get_loc(c)) for c in self.cat_features]
-            # params["categorical_feature"] = ",".join(cat_indices)
             x = fill_na_cat_features(x, self.cat_features)
             if self.cat_encoder is not None:
-                x[self.cat_features] = self.cat_encoder.transform(x[self.cat_features])
-            # for feature in self.cat_features:
-            #     encoder = self.cat_features_encoders[feature]
-            #     x[feature] = encoder.transform(x[feature])
-                # x[feature] = x[feature].astype("category").cat.codes
+                x[self.cat_features] = pd.DataFrame(
+                    self.cat_encoder.transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
+                )
         if not is_numeric_dtype(y):
             y_numpy = correct_string_target(y_numpy)
         return x, y_numpy, params

upgini/utils/target_utils.py

@@ -297,9 +297,9 @@ def balance_undersample_time_series_trunc(
     time_unit_threshold: pd.Timedelta = DEFAULT_TIME_UNIT_THRESHOLD,
     **kwargs,
 ):
-    # Convert date column to datetime
     if id_columns is None:
-        id_columns = [date_column]
+        id_columns = []
+    # Convert date column to datetime
     dates_df = df[id_columns + [date_column]].copy()
     dates_df[date_column] = pd.to_datetime(dates_df[date_column], unit="ms")
 

{upgini-1.2.71a3832.dev13.dist-info → upgini-1.2.72.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.71a3832.dev13
+Version: 1.2.72
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.71a3832.dev13.dist-info → upgini-1.2.72.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=buorll9F2OX4EgV8VmlIrj09nqmsSmqAG8T8p6hRCls,34
+upgini/__about__.py,sha256=-EK4ypqJTIRrg6g1P6PtLXT9vC4Vq7zblqFi389VgwA,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=lk80Bx9U36lva6T4lPHBFk88ivrpZ-2uwwMwQg0LglE,207023
+upgini/features_enricher.py,sha256=Li1sPihWVkPUPcma8HRbPFwpCqd9V9d2p5zQUgkpdpU,206998
 upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=ot6AhxfRRTzM-dNApWTvmteLBAmGjD9OyAuKmtUTprE,40630
+upgini/metrics.py,sha256=a0bY4oTMb-MgB1yC1IuTcEtotKZxAxjgV_QV2Z4V8u4,38988
 upgini/search_task.py,sha256=EuCGp0iCWz2fpuJgN6M47aP_CtIi3Oq9zw78w0mkKiU,17595
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -66,11 +66,11 @@ upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=HpaNQaKJisgNE7IZ71n7uswxTj7kbPglU2G3s1sORAc,45042
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
-upgini/utils/target_utils.py,sha256=KNFzJta1SpGU4sp07dHKSeVJlDs_9qgD2wcw5YuJfOc,16661
+upgini/utils/target_utils.py,sha256=P0cCVRaakWLydYwFjk3TEaQfr0p0hfsJCvKRD8qcxiE,16650
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.71a3832.dev13.dist-info/METADATA,sha256=JdRugxJAMW4KLyRuz7yIX_PqSz_nObynmhkW5-g_lVs,49102
-upgini-1.2.71a3832.dev13.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.71a3832.dev13.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.71a3832.dev13.dist-info/RECORD,,
+upgini-1.2.72.dist-info/METADATA,sha256=OpaT2gblO8qGzEJBNf36-dPwbedHPP93bX0fPAOMl38,49091
+upgini-1.2.72.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.72.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.72.dist-info/RECORD,,